INDEX

Explanations

just plug

The neuron is activating on content‐bearing tokens (nouns, verbs, adjectives, adverbs—i.e. “meaningful” words) and not on function words or punctuation.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ଂ

-1.30

 πολι

-1.27

 السياس

-1.27

 делает

-1.16

对话框

-1.16

 ofrecer

-1.15

pvp

-1.13

 ayudar

-1.13

 лекарства

-1.13

 زيادة

-1.13

POSITIVE LOGITS

 your

2.55

you

2.20

 yourself

1.60

 will

1.58

如果你

1.20

 متوسط

1.19

 dann

1.18

 here

1.16

You

1.13

 вам

1.13

Activations Density 0.015%